6 May 2022 in Neural Computing and Applications
Non-motor manifestations of Parkinson’s disease (PD) appear early and have a significant impact on the quality of life of patients, but few studies have evaluated their predictive potential with machine learning algorithms. We evaluated 9 algorithms for discriminating PD patients from controls using a wide collection of non-motor clinical PD features from two databases: Biocruces (96 subjects) and PPMI (687 subjects). In addition, we evaluated whether the combination of both databases could improve the individual results. For each database 2 versions with different granularity were created and a feature selection process was performed. We observed that most of the algorithms were able to detect PD patients with high accuracy (>80%). Support Vector Machine and Multi-Layer Perceptron obtained the best performance, with an accuracy of 86.3% and 84.7%, respectively. Likewise, feature selection led to a significant reduction in the number of variables and to better performance. Besides, the enrichment of Biocruces database with data from PPMI moderately benefited the performance of the classification algorithms, especially the recall and to a lesser extent the accuracy, while the precision worsened slightly. The use of interpretable rules obtained by the RIPPER algorithm showed that simply using two variables (autonomic manifestations and olfactory dysfunction), it was possible to achieve an accuracy of 84.4%. Our study demonstrates that the analysis of non-motor parameters of PD through machine learning techniques can detect PD patients with high accuracy and recall, and allows us to select the most discriminative non-motor variables to create potential tools for PD screening.
1 May 2015 in Parkinsonism & Related Disorders
25 February 2021 in Journal of Neurology
31 January 2025 in Acta Neuropathologica Communications
Parkinson’s disease (PD) is a neurodegenerative disorder primarily characterized by motor symptoms, with emerging evidence suggesting retinal pathology, particularly in the ganglion cell-inner plexiform layer (GCIPL), detectable via optical coherence tomography (OCT). This study aimed to characterize early retinal dynamics in PD using OCT. We conducted a prospective one-year longitudinal multicenter study involving 53 early-stage PD patients with a disease duration of 5 years or less and 52 controls. The participants underwent retinal spectral-domain OCT, primary visual function and cognitive examinations. We examined baseline retinal measures and short-term longitudinal differences between groups via linear mixed effects models. In PD patients, the baseline GCIPL thickness in central regions was increased by up to 4 μm, and the rate of thinning in the parafoveal GCIPL was − 0.61 [0.29] µm/year faster over a one-year follow-up period than in controls in the 2- to 3-mm ring (p = 0.039). In PD patients, greater central GCIPL thickness was associated with poorer contrast sensitivity and reduced performance on the Farnsworth D15 color vision test. It also predicted subsequent thinning in both the GCIPL (2- to 3-mm ring) and the inner nuclear layer (2- to 5-mm rings). However, this increased thickness was not linked to prevalent or progressive motor or cognitive manifestations. In conclusion, this study provides the first detailed topographical description of early retinal dynamics in PD patients, revealing increased central GCIPL thickness and accelerated parafoveal GCIPL thinning in PD. However, the macular region shows complex and variable dynamics among PD patients, but these changes precede detectable progression in clinical scales.
1 November 2023 in Neurología
Multiple system atrophy is a rare and fatal neurodegenerative disorder, characterized by autonomic dysfunction in association with either parkinsonism or cerebellar signs. The pathologic hallmark is the presence of alpha-synuclein aggregates in oligodendrocytes, forming glial cytoplasmic inclusions. Clinically, it may be difficult to distinguish form other parkinsonisms or ataxias, particularly in the early stages of the disease. In this case series we aim to describe in detail the features of MSA patients. Unified MSA Rating Scale (UMSARS) score, structural and functional imaging and cardiovascular autonomic testing, are summarized since early stages of the disease. UMSARS proved to be useful to perform a follow-up being longitudinal examination essential to stratify risk of poor outcome. Neuropathological diagnosis showed an overlap between parkinsonian and cerebellar subtypes, with some peculiarities that could help to distinguish from other subtypes. A better description of MSA features with standardized test confirmed by means of neuropathological studies could help to increase sensitivity.